Distinguishing Neighborhood Representations Through Reverse Process of GNNs for Heterophilic Graphs

arXiv:2403.10543v1 Announce Type: cross
Abstract: Graph Neural Network (GNN) resembles the diffusion process, leading to the over-smoothing of learned representations when stacking many layers. Hence, the reverse process of message passing can sharpen the node representations by inverting the forward message propagation. The sharpened representations can help us to better distinguish neighboring nodes with different labels, such as in heterophilic graphs. In this work, we apply the design principle of the reverse process to the three variants of the GNNs. …

abstract arxiv cs.lg cs.si diffusion gnn gnns graph graph neural network graphs network neural network node process propagation through type